{"id":"https://openalex.org/W7166862012","doi":"https://doi.org/10.18653/v1/2026.acl-long.733","title":"CoLA: A Choice Leakage Attack Framework to Expose Privacy Risks in Subset Training","display_name":"CoLA: A Choice Leakage Attack Framework to Expose Privacy Risks in Subset Training","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166862012","doi":"https://doi.org/10.18653/v1/2026.acl-long.733"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.acl-long.733","doi":"https://doi.org/10.18653/v1/2026.acl-long.733","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.733","pdf_url":"https://aclanthology.org/2026.acl-long.733.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.acl-long.733.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139801507","display_name":"Qi Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133647860","display_name":"Cheng-Long Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Cheng-Long Wang","raw_affiliation_strings":["King Abdullah University of Science and Technology","Provable Responsible AI and Data Analytics Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King Abdullah University of Science and Technology","institution_ids":["https://openalex.org/I71920554"]},{"raw_affiliation_string":"Provable Responsible AI and Data Analytics Lab","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139790247","display_name":"Yinzhi Cao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yinzhi Cao","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100401482","display_name":"Di Wang","orcid":"https://orcid.org/0000-0003-4908-0243","observed_orcids":["https://orcid.org/0000-0003-4908-0243","https://orcid.org/0009-0001-5741-6694"]},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Di Wang","raw_affiliation_strings":["King Abdullah University of Science and Technology","Provable Responsible AI and Data Analytics Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King Abdullah University of Science and Technology","institution_ids":["https://openalex.org/I71920554"]},{"raw_affiliation_string":"Provable Responsible AI and Data Analytics Lab","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.46608781,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"16137","last_page":"16149"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9115999937057495,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9115999937057495,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.0869000032544136,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11045","display_name":"Privacy, Security, and Data Protection","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/membership-inference-attacks","display_name":"membership inference attacks","score":0.7699999809265137},{"id":"https://openalex.org/keywords/black-box-attacks","display_name":"black-box attacks","score":0.9340000152587891}],"concepts":[{"id":"https://openalex.org/C2779137570","wikidata":"https://www.wikidata.org/wiki/Q16243196","display_name":"EXPOSE","level":2,"score":0.9180999994277954},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.6427000164985657},{"id":"https://openalex.org/C2777042071","wikidata":"https://www.wikidata.org/wiki/Q6509304","display_name":"Leakage (economics)","level":2,"score":0.5669000148773193},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5365999937057495},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5001999735832214},{"id":"https://openalex.org/C165609540","wikidata":"https://www.wikidata.org/wiki/Q1172486","display_name":"Data breach","level":2,"score":0.42160001397132874},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.3917999863624573},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.3578000068664551},{"id":"https://openalex.org/C3017597292","wikidata":"https://www.wikidata.org/wiki/Q25052250","display_name":"Privacy protection","level":2,"score":0.3522999882698059},{"id":"https://openalex.org/C2779201187","wikidata":"https://www.wikidata.org/wiki/Q2775060","display_name":"Information leakage","level":2,"score":0.34200000762939453},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.30970001220703125},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C71745522","wikidata":"https://www.wikidata.org/wiki/Q2476929","display_name":"Confidentiality","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.2646999955177307},{"id":"https://openalex.org/C12174686","wikidata":"https://www.wikidata.org/wiki/Q1058438","display_name":"Risk assessment","level":2,"score":0.25440001487731934}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.733","doi":"https://doi.org/10.18653/v1/2026.acl-long.733","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.733","pdf_url":"https://aclanthology.org/2026.acl-long.733.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.733","doi":"https://doi.org/10.18653/v1/2026.acl-long.733","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.733","pdf_url":"https://aclanthology.org/2026.acl-long.733.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G4795079661","display_name":null,"funder_award_id":"BAS/1/1689-01-01","funder_id":"https://openalex.org/F4320322320","funder_display_name":"King Abdullah University of Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320322320","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166862012.pdf","grobid_xml":"https://content.openalex.org/works/W7166862012.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7170138441","https://openalex.org/W7221381635","https://openalex.org/W4415233577","https://openalex.org/W7171710893","https://openalex.org/W4391912718","https://openalex.org/W2898291644","https://openalex.org/W6966696245","https://openalex.org/W7167900452","https://openalex.org/W7223201172","https://openalex.org/W4226277587"],"abstract_inverted_index":{"Training":[0],"models":[1,212,217,236],"on":[2,43,130,208],"a":[3,16,118],"carefully":[4],"chosen":[5],"portion":[6],"of":[7,68,104,134,170,183,197],"data":[8,70,172],"rather":[9],"than":[10],"the":[11,65,96,102,105,131,135,168,181,189,195,203,222,238],"full":[12],"dataset":[13],"is":[14,40,61],"now":[15],"standard":[17],"preprocess":[18],"for":[19,121],"modern":[20],"ML.From":[21],"vision":[22,209],"coreset":[23],"selection":[24,98,191,230],"to":[25,158,202,237],"large-scale":[26],"filtering":[27],"in":[28,125,188],"language":[29,211],"models,":[30],"it":[31],"enables":[32],"scalability":[33],"with":[34],"minimal":[35],"utility":[36],"loss.A":[37],"common":[38],"intuition":[39],"that":[41,58,186,214],"training":[42,60,171,201,228],"fewer":[44],"samples":[45,185],"should":[46],"also":[47],"reduce":[48],"privacy":[49,63,78,123,155,169,182,220,224],"risks.In":[50],"this":[51,55,110],"paper,":[52],"we":[53,112,138,152],"challenge":[54],"assumption.We":[56],"show":[57,213],"subset":[59,97,126,159,190],"not":[62],"free:":[64],"very":[66],"choices":[67],"which":[69,165,179],"are":[71],"included":[72],"or":[73,100],"excluded":[74],"can":[75,86],"introduce":[76],"new":[77],"surface":[79,225],"and":[80,147,174,210,229],"leak":[81],"more":[82],"sensitive":[83],"information.Such":[84],"information":[85],"be":[87],"captured":[88],"by":[89],"adversaries":[90],"either":[91],"through":[92],"side-channel":[93,136],"metadata":[94],"from":[95,199,234],"process":[99],"via":[101],"outputs":[103],"target":[106],"model.To":[107],"systematically":[108],"study":[109],"phenomenon,":[111],"propose":[113],"CoLA":[114],"(Choice":[115],"Leakage":[116],"Attack),":[117],"unified":[119],"framework":[120],"analyzing":[122],"leakage":[124],"selection.In":[127],"CoLA,":[128],"depending":[129],"adversary's":[132],"knowledge":[133],"information,":[137],"define":[139],"two":[140,154],"practical":[141],"attack":[142],"scenarios:":[143],"Subsetaware":[144],"Side-channel":[145],"Attacks":[146],"Black-box":[148],"Attacks.Under":[149],"both":[150,227],"scenarios,":[151],"investigate":[153],"surfaces":[156],"unique":[157],"training:":[160],"(1)":[161],"Training-membership":[162],"MIA":[163,177],"(TM-MIA),":[164],"concerns":[166,180],"only":[167],"membership,":[173,231],"(2)":[175],"Selection-participation":[176],"(SP-MIA),":[178],"all":[184],"participated":[187],"process.Notably,":[192],"SP-MIA":[193],"enlarges":[194],"notion":[196],"membership":[198],"model":[200],"entire":[204],"data-model":[205],"supply":[206],"chain.Experiments":[207],"existing":[215],"threat":[216],"underestimate":[218],"subset-training":[219],"risks:":[221],"expanded":[223],"leaks":[226],"extending":[232],"risks":[233],"individual":[235],"broader":[239],"ML":[240],"ecosystem.":[241]},"counts_by_year":[],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2026-07-02T00:00:00"}